基于CWT和CNN的振动时间频率特征的滑状态识别
1Yazhou Bay Innovation Institute, International Navigation College, Hainan Tropical Ocean University, Sanya, 572022, China.
Scientific reports
|August 7, 2025
概括
本研究引入了一种使用连续波纹变换 (CWT) 和卷积神经网络 (CNN) 进行精确滑监测的新方法. 该技术可靠地识别机械系统中的正常,不足和受污染的滑状态.
科学领域:
- 机械工程 机械工程
- 部落学 (tribology) 是一个学科.
- 信号处理 信号处理
- 人工智能的人工智能
背景情况:
- 滑对于机械系统的可靠性至关重要,但降解会导致故障.
- 监测滑状态 (正常,不足,受污染) 对于预测性维护至关重要.
- 目前用于滑状态识别的方法在准确性和稳定性方面存在局限性.
研究的目的:
- 开发一种使用振动信号识别滑状态的新且强大的方法.
- 整合连续波形变换 (CWT) 与卷积神经网络 (CNN) 进行增强的特征提取和分类.
- 评估拟议方法的性能与传统技术相比.
主要方法:
- 在三种滑条件下,从针盘式三极管学系统收集了振动信号.
- 应用连续波纹转换 (CWT) 将振动信号转换为时间频率图.
- 开发和训练了一个卷积神经网络 (CNN) 模型,使用CWT生成的图表进行分类.
主要成果:
- 在CWT+CNN模型中,训练准确率达到99.8%,测试准确率达到100%.
- 提出的方法显著优于传统方法 (例如,RMS+CNN,PSD+CNN,CWT+SVM).
- t-SNE可视化和混矩阵证实了明显的特征分离和完美的分类.
结论:
- 集成的CWT和CNN方法为滑状态监控提供了高度准确和可靠的解决方案.
- 这种方法有效地捕获了关键的时间频率特征,以进行可靠的故障诊断.
- 这些发现为设备健康管理中的实际工业应用提供了有前途的工具.
相关概念视频
Design Example: Deciding Thickness of Lubricating Fluid in a Shaft
155
Effective lubrication between a rotating shaft and its bearing housing is essential in rotating machinery to minimize friction, wear, and energy loss. With carefully controlled thickness and viscosity, the lubricant layer prevents metal-to-metal contact, ensuring smooth operation.
To calculate the required thickness of the lubricant layer, the tangential velocity at the shaft's surface must first be determined. This velocity is calculated by converting the rotational speed to angular...
To calculate the required thickness of the lubricant layer, the tangential velocity at the shaft's surface must first be determined. This velocity is calculated by converting the rotational speed to angular...
155
Discrete Fourier Transform
411
The Discrete Fourier Transform (DFT) is a fundamental tool in signal processing, extending the discrete-time Fourier transform by evaluating discrete signals at uniformly spaced frequency intervals. This transformation converts a finite sequence of time-domain samples into frequency components, each representing complex sinusoids ordered by frequency. The DFT translates these sequences into the frequency domain, effectively indicating the magnitude and phase of each frequency component present...
411
Linear time-invariant Systems
420
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
420


